garmin-owl

by xichen-de

Overview Schema Source Related Servers Discussions Admin

Python

Local

get_cycle

Read-only

Fetch normalized cycle phase, day, timing, and Garmin predictions for one date to provide cycle context.

Instructions

Get normalized cycle phase, day, timing, and Garmin predictions for one date.

Use for cycle context on one date; use get_recovery or get_recovery_trend to relate the phase to sleep, HRV, and resting HR. Private notes, symptoms, moods, and raw daily logs are excluded.

Field notes: phase is menstruation, follicular, ovulation, or luteal; day_in_cycle counts from cycle_start_date (day 1). Predictions are Garmin's own and may be absent. The fertile window is calculated by garmin-owl from Garmin's offsets, and availability says so.

Requires saved local Garmin authentication (garmin-owl-auth). Reads Garmin and may update the local cache; never changes your Garmin account. Garmin failures are not retried automatically.

Input Schema

Name	Required	Description	Default
`date`	No	Calendar date in YYYY-MM-DD format, e.g. 2026-10-09; any past date Garmin still stores. Omit or pass null for today in the server's local timezone.

Output Schema

Name	Required	Description	Default
`date`	Yes
`phase`	No
`cycle_type`	No
`phase_code`	No
`availability`	No
`day_in_cycle`	No
`cycle_start_date`	No
`fertile_window_end`	No
`period_length_days`	No
`fertile_window_start`	No
`days_until_next_phase`	No
`next_predicted_cycle_start`	No
`predicted_cycle_length_days`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv0.3.1Oct 24, 2026

changedInput schema / properties / date / anyOf

Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / date / description

Added value: +"Calendar date in YYYY-MM-DD format, e.g. 2026-10-09; any past date Garmin still stores. Omit or pass null for today in the server's local timezone."

addedOutput schema / $defs

Added value: +{
+  "AvailabilityNotice": {
+    "properties": {
+      "field": {
+        "title": "Field",
+        "type": "string"
+      },
+      "message": {
+        "title": "Message",
+        "type": "string"
+      },
+      "status": {
+        "title": "Status",
+        "type": "string"
+      }
+    },
+    "required": [
+      "field",
+      "status",
+      "message"
+    ],
+    "title": "AvailabilityNotice",
+    "type": "object"
+  }
+}

removedOutput schema / additionalProperties
```
Removed value: -true
```

addedOutput schema / properties

Added value: +{
+  "availability": {
+    "items": {
+      "$ref": "#/$defs/AvailabilityNotice"
+    },
+    "title": "Availability",
+    "type": "array"
+  },
+  "cycle_start_date": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Cycle Start Date"
+  },
+  "cycle_type": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Cycle Type"
+  },
+  "date": {
+    "title": "Date",
+    "type": "string"
+  },
+  "day_in_cycle": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Day In Cycle"
+  },
+  "days_until_next_phase": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Days Until Next Phase"
+  },
+  "fertile_window_end": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Fertile Window End"
+  },
+  "fertile_window_start": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Fertile Window Start"
+  },
+  "next_predicted_cycle_start": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Next Predicted Cycle Start"
+  },
+  "period_length_days": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Period Length Days"
+  },
+  "phase": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Phase"
+  },
+  "phase_code": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Phase Code"
+  },
+  "predicted_cycle_length_days": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Predicted Cycle Length Days"
+  }
+}

addedOutput schema / required
```
Added value: +[
+  "date"
+]
```

changedOutput schema / title

Previous value: -"get_cycleDictOutput"New value: +"CycleSummary"

First observedv0.1.0Aug 31, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, but the description adds important operational context: saved Garmin authentication is required, local cache may be updated, the Garmin account is never changed, and failures are not retried. It also discloses privacy boundaries and field semantics beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose and usage guidance, then moves into field notes and operational caveats. It is somewhat dense but each sentence adds useful information for selecting and invoking the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so the description does not need to explain return values, yet it still clarifies phase values, day_in_cycle counting, prediction availability, and the fertile-window calculation. Authentication, cache behavior, and failure handling are also covered, making the definition complete for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already has 100% description coverage for the single 'date' parameter, including format and default behavior. The description says 'for one date' but does not add syntax or interpretation beyond the schema, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Get normalized cycle phase, day, timing, and Garmin predictions for one date.' It also distinguishes the tool from siblings by pointing to get_recovery and get_recovery_trend for broader recovery context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says when to use this tool ('for cycle context on one date') and names alternatives for related questions ('use get_recovery or get_recovery_trend to relate the phase to sleep, HRV, and resting HR'). It further clarifies scope by excluding private notes, symptoms, moods, and raw daily logs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.